Semi-Supervised Class Incremental Learning

This paper makes a contribution to the problem of incremental class learning, the principle of which is to sequentially introduce batches of samples annotated with new classes during the learning phase. The main objective is to reduce the drop in classification performance on old classes, a phenomenon commonly called catastrophic forgetting. We propose in this paper a new method which exploits the availability of a large quantity of non-annotated images in addition to the annotated batches. These images are used to regularize the classifier and give the feature space a more stable structure. We demonstrate on two image data sets, MNIST and STL-10, that our approach is able to improve the global performance of classifiers learned using an incremental learning protocol, even with annotated batches of small size.

[1]  Cordelia Schmid,et al.  End-to-End Incremental Learning , 2018, ECCV.

[2]  Marcus Rohrbach,et al.  Memory Aware Synapses: Learning what (not) to forget , 2017, ECCV.

[3]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[4]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Shutao Xia,et al.  Maintaining Discrimination and Fairness in Class Incremental Learning , 2019, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[8]  Yen-Cheng Liu,et al.  Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines , 2018, ArXiv.

[9]  Honglak Lee,et al.  An Analysis of Single-Layer Networks in Unsupervised Feature Learning , 2011, AISTATS.

[10]  Yandong Guo,et al.  Large Scale Incremental Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yandong Guo,et al.  Incremental Classifier Learning with Generative Adversarial Networks , 2018, ArXiv.

[12]  R. French.  Catastrophic forgetting in connectionist networks , 1999, Trends in Cognitive Sciences.

[13]  Gregory Cohen,et al.  EMNIST: Extending MNIST to handwritten letters , 2017, 2017 International Joint Conference on Neural Networks (IJCNN).

[14]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[16]  Nikos Komodakis,et al.  Unsupervised Representation Learning by Predicting Image Rotations , 2018, ICLR.

[17]  Kibok Lee,et al.  Overcoming Catastrophic Forgetting With Unlabeled Data in the Wild , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[18]  Larry P. Heck,et al.  Class-incremental Learning via Deep Model Consolidation , 2019, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[19]  Pascal Vincent,et al.  Unsupervised Feature Learning and Deep Learning: A Review and New Perspectives , 2012, ArXiv.

[20]  Navdeep Jaitly,et al.  Adversarial Autoencoders , 2015, ArXiv.

[21]  Yoshua Bengio,et al.  An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.

[22]  Alexander Kolesnikov,et al.  Revisiting Self-Supervised Visual Representation Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Andreas S. Tolias,et al.  Three scenarios for continual learning , 2019, ArXiv.